blzheng 797c7e2802 [Quant][PT2E]change flatten recipe for X86InductorQuantizer (#136298) ... This PR modifies the flatten recipe: if none of the users of the flatten node are quantizable ops, int8 flatten will be disabled to avoid unnecessary dtype conversions. Pull Request resolved: https://github.com/pytorch/pytorch/pull/136298 Approved by: https://github.com/leslie-fang-intel, https://github.com/jgong5		2024-09-24 04:30:12 +00:00
..
ao_migration
bc
core	Add uint16 support for observer (#136238)	2024-09-18 23:52:18 +00:00
eager
fx
jit
pt2e	[Quant][PT2E]change flatten recipe for X86InductorQuantizer (#136298)	2024-09-24 04:30:12 +00:00
serialized
__init__.py